© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 3223
    Prev
    Next
    INDEX
    Explanations

    complex mathematical notation including symbols like theta, psi, and mu

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     Wikimedijinoj
    -1.05
     gynnwys
    -1.02
     تضيفلها
    -0.91
     мәкал
    -0.90
    IANGLES
    -0.84
    CppMethod
    -0.82
    WillAppear
    -0.75
    ThroughAttribute
    -0.75
     مشين
    -0.74
    ///</
    -0.73
    POSITIVE LOGITS
     maternelle
    0.61
    unggulan
    0.50
     gynhyrchwyd
    0.49
     تعدى
    0.41
     Another
    0.40
     propio
    0.40
     actualité
    0.40
     Streit
    0.39
     another
    0.38
    ArgumentParser
    0.38
    Activations Density 1.947%

    No Known Activations